# BEVT: BERT Pretraining of Video Transformers

arXiv: https://arxiv.org/abs/2112.01529 · HTML: https://mlsanity.com/paper/2112.01529/

## Key facts

- Cited by 169 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 73 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 30 of 66)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)

## Built on by (most cited first, 30 of 169)

- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2208.12262/) (2022)
- [SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2211.14813/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [OmniVL:One Foundation Model for Image-Language and Video-Language Tasks](https://mlsanity.com/paper/2209.07526/) (2022)
- [OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation](https://mlsanity.com/paper/2406.09399/) (2024)
- [Image and Video Tokenization with Binary Spherical Quantization](https://mlsanity.com/paper/2406.07548/) (2024)
- [OmniMAE: Single Model Masked Pretraining on Images and Videos](https://mlsanity.com/paper/2206.08356/) (2022)
- [Protecting Celebrities from DeepFake with Identity Consistency Transformer](https://mlsanity.com/paper/2203.01318/) (2022)
- [Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2212.04500/) (2022)
- [Self-Supervised Learning for Videos: A Survey](https://mlsanity.com/paper/2207.00419/) (2022)
- [AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?](https://mlsanity.com/paper/2307.16368/) (2023)
- [GIVT: Generative Infinite-Vocabulary Transformers](https://mlsanity.com/paper/2312.02116/) (2023)
- [ObjectFormer for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2203.14681/) (2022)
- [Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning](https://mlsanity.com/paper/2207.04978/) (2022)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling](https://mlsanity.com/paper/2209.01540/) (2022)
- [CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment](https://mlsanity.com/paper/2209.06430/) (2022)
- [SVFormer: Semi-supervised Video Transformer for Action Recognition](https://mlsanity.com/paper/2211.13222/) (2022)
- [ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System](https://mlsanity.com/paper/2304.14407/) (2023)
- [Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges](https://mlsanity.com/paper/2404.16112/) (2024)

## Abstract (arXiv)

This paper studies the BERT pretraining of video transformers. It is a straightforward but worth-studying extension given the recent success from BERT pretraining of image transformers. We introduce BEVT which decouples video representation learning into spatial representation learning and temporal dynamics learning. In particular, BEVT first performs masked image modeling on image data, and then conducts masked image modeling jointly with masked video modeling on video data. This design is motivated by two observations: 1) transformers learned on image datasets provide decent spatial priors that can ease the learning of video transformers, which are often times computationally-intensive if trained from scratch; 2) discriminative clues, i.e., spatial and temporal information, needed to make correct predictions vary among different videos due to large intra-class and inter-class variations. We conduct extensive experiments on three challenging video benchmarks where BEVT achieves very promising results. On Kinetics 400, for which recognition mostly relies on discriminative spatial representations, BEVT achieves comparable results to strong supervised baselines. On Something-Something-V2 and Diving 48, which contain videos relying on temporal dynamics, BEVT outperforms by clear margins all alternative baselines and achieves state-of-the-art performance with a 71.4% and 87.2% Top-1 accuracy respectively. Code will be made available at urlhttps://github.com/xyzforever/BEVT.